Bidirectional skip-frame prediction for video anomaly detection with intra-domain disparity-driven attention

TL;DR

This paper introduces a bidirectional skip-frame prediction network for video anomaly detection that leverages intra-domain disparity and attention mechanisms to improve the discrimination between normal and abnormal events, achieving superior results on benchmark datasets.

Contribution

The paper proposes a novel bidirectional skip-frame prediction network with intra-domain disparity-driven attention for enhanced video anomaly detection.

Findings

Outperforms state-of-the-art methods on four benchmark datasets

Effectively expands disparity between normal and abnormal events

Utilizes dual-stream autoencoder with attention mechanisms

Abstract

With the widespread deployment of video surveillance devices and the demand for intelligent system development, video anomaly detection (VAD) has become an important part of constructing intelligent surveillance systems. Expanding the discriminative boundary between normal and abnormal events to enhance performance is the common goal and challenge of VAD. To address this problem, we propose a Bidirectional Skip-frame Prediction (BiSP) network based on a dual-stream autoencoder, from the perspective of learning the intra-domain disparity between different features. The BiSP skips frames in the training phase to achieve the forward and backward frame prediction respectively, and in the testing phase, it utilizes bidirectional consecutive frames to co-predict the same intermediate frames, thus expanding the degree of disparity between normal and abnormal events. The BiSP designs the variance channel attention and context spatial attention from the perspectives of movement patterns and object scales, respectively, thus ensuring the maximization of the disparity between normal and abnormal in the feature extraction and delivery with different dimensions. Extensive experiments from four benchmark datasets demonstrate the effectiveness of the proposed BiSP, which substantially outperforms state-of-the-art competing methods.